In this study an information filtering system was implemented and a series of relevance feedback experiments were conducted using the system. For the relevance feedback, the original queries were searched against the database and the results were reviewed by the researchers. Based on users' online relevance judgements a pair of 17 refined queries were generated using two methods called "co-occurrence exclusion method" and "lower frequencies exclusion method." In order to generate them, the original queries. the descriptors and category codes appeared in either relevant or irrelevant document sets were applied as elements. Users' relevance judgments on the search results of the refined queries were compared and analyzed against those of the original queries. [ 더 많은 내용 보기 ]